joey00072 / nanoGRPOLinks
nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)
☆105Updated 3 weeks ago
Alternatives and similar repositories for nanoGRPO
Users that are interested in nanoGRPO are comparing it to the libraries listed below
Sorting:
- minimal GRPO implementation from scratch☆90Updated 2 months ago
- Official repo of paper LM2☆40Updated 3 months ago
- ☆114Updated 3 months ago
- ☆113Updated 4 months ago
- RL significantly the reasoning capability of Qwen2.5-1.5B-Instruct☆29Updated 3 months ago
- Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆90Updated 2 months ago
- Exploring Applications of GRPO☆229Updated 2 weeks ago
- Tina: Tiny Reasoning Models via LoRA☆245Updated this week
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆171Updated 4 months ago
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate"☆151Updated last month
- ☆97Updated 11 months ago
- A simplified implementation for experimenting with RLVR on GSM8K, This repository provides a starting point for exploring reasoning.☆95Updated 3 months ago
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆170Updated 5 months ago
- Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models☆54Updated last month
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆119Updated this week
- ☆188Updated 3 months ago
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆88Updated last week
- A brief and partial summary of RLHF algorithms.☆128Updated 3 months ago
- This is the official repository for Inheritune.☆111Updated 3 months ago
- ☆86Updated 2 weeks ago
- ☆79Updated 9 months ago
- Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling☆102Updated 4 months ago
- A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).☆248Updated last week
- ☆92Updated 8 months ago
- NeurIPS 2024 tutorial on LLM Inference☆45Updated 5 months ago
- Code for the paper: "Learning to Reason without External Rewards"☆237Updated this week
- An Open Math Pre-trainng Dataset with 370B Tokens.☆87Updated 2 months ago
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆94Updated 2 months ago
- Minimal hackable GRPO implementation☆232Updated 4 months ago
- A (somewhat) minimal library for finetuning language models with PPO on human feedback.☆85Updated 2 years ago